))
AI in Dentistry: Diagnosing TMD with MRIs
Manage episode 444599857 series 3605861
Innehåll tillhandahållet av Brian Carter. Allt poddinnehåll inklusive avsnitt, grafik och podcastbeskrivningar laddas upp och tillhandahålls direkt av Brian Carter eller deras podcastplattformspartner. Om du tror att någon använder ditt upphovsrättsskyddade verk utan din tillåtelse kan du följa processen som beskrivs här https://sv.player.fm/legal.
This research paper proposes an AI-driven diagnostic system for Temporomandibular Joint Disorders (TMD) using MRI images. The system employs a segmentation method to identify key anatomical structures like the temporal bone, temporomandibular joint (TMJ) disc, and condyle. Using these identified structures, the system utilizes a decision tree based on their geometrical relationship to classify a patient as having TMD or not. The paper details the system’s development, including data acquisition, preprocessing, model training, and inferencing. The system is evaluated through a k-fold cross-validation, and its performance is assessed based on various metrics like sensitivity, specificity, accuracy, and F1-score. The results suggest that the AI-driven TMD diagnostic system demonstrates significant potential in assisting radiologists with TMJ diagnosis, although further improvements and validation using larger and more diverse datasets are required to enhance its performance and generalizability.
Read more: https://arxiv.org/pdf/2402.03397
71 episoder
Dela
